Method for identifying 3D model based on sparse coding
A sparse self-encoding and three-dimensional model technology, applied in the field of three-dimensional model recognition, can solve the problem of large redundancy between data and achieve the effect of improving the recognition effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0066] Concrete examples
[0067] One, the database
[0068] The database used in this experiment is the NTU (Nanyang Technological University) database published by Nanyang Technological University, Singapore, which is well known in the art. The NTU database includes 47 categories and a total of 549 different virtual 3D models, such as apples, water bottles, sailboats, seats, etc. We placed the virtual three-dimensional model in the center of the sphere, and placed the virtual camera on each vertex of the C60 structure to take 60 two-dimensional views.
[0069] 2. Parameter setting
[0070] In the embodiment of the present invention, the specific parameter values are: l=8, d=3, s=1, m=240, K=128.
[0071] 3. Evaluation Criteria
[0072] Precision-recall curve (PR, Precision-recall curve): It mainly describes the dynamic relationship between recall and precision based on the similarity list. A good PR curve should be as close as possible to the upper right side of the coordinate axi...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap